Related papers: PennySynth: RAG-Driven Data Synthesis for Automate…

Context: Due to the demand for strong algorithmic reasoning, complex logic implementation, and strict adherence to input/output formats and resource constraints, competitive programming generation by large language models (LLMs) is…

We present ongoing work on a new automatic code generation approach for supporting quantized generative inference on LLMs such as LLaMA or OPT on off-the-shelf CPUs. Our approach is informed by the target architecture and a performance…

Large language models (LLMs) can generate code rapidly but remain unreliable for scientific algorithms whose correctness depends on structural assumptions rarely explicit in the source literature. We introduce a multi-stage LLM-assisted…

Large Language Models (LLMs) demonstrate human-level capabilities in dialogue, reasoning, and knowledge retention. However, even the most advanced LLMs face challenges such as hallucinations and real-time updating of their knowledge.…

Generative machine learning models for exploring chemical space have shown immense promise, but many molecules they generate are too difficult to synthesize, making them impractical for further investigation or development. In this work, we…

Automating penetration testing is crucial for enhancing cybersecurity, yet current Large Language Models (LLMs) face significant limitations in this domain, including poor error handling, inefficient reasoning, and an inability to perform…

Retrieval-Augmented Code Generation (RACG) leverages external knowledge to enhance Large Language Models (LLMs) in code synthesis, improving the functional correctness of the generated code. However, existing RACG systems largely overlook…

Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…

While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse programming tasks. Dynamically selecting the optimal LLM…

Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved strong performance at the function and file levels, real-world software engineering requires…

Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies…

While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate…

In recent years, the advancement of quantum computing technology has posed potential security threats to RSA cryptography and elliptic curve cryptography. In response, the National Institute of Standards and Technology (NIST) published…

In modern software development, developers frequently need to understand code behavior at a glance -- whether reviewing pull requests, debugging issues, or navigating unfamiliar codebases. This ability to reason about dynamic program…

Contextual embeddings generated by LLMs exhibit strong positional inductive biases, which can limit their ability to fully capture long-range, order-sensitive dependencies in highly structured source code. Consequently, how to further…

Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical…

Recent advancements in large language models (LLMs) have sparked significant interest in the automatic generation of Register Transfer Level (RTL) designs, particularly using Verilog. Current research on this topic primarily focuses on…

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts,…

Document-level knowledge graph (KG) construction faces a fundamental scaling challenge: existing methods either rely on expensive large language models (LLMs), making them economically nonviable for large-scale corpora, or employ smaller…

Automated code generation can systematically exceed expert hand-optimization for recurrence relations-computational primitives ubiquitous in orthogonal polynomials, special functions, numerical integration, and molecular integral…